Pith. sign in

REVIEW 3 cited by

Face Transformer for Recognition

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.14803 v2 pith:EZYZ4PAU submitted 2021-03-27 cs.CV

Yaoyao Zhong , Weihong Deng This is my paper · ORCID
classification cs.CV
keywords transformerfacemodelsrecognitiondatabasesms-celeb-1mperformancetrained
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently there has been a growing interest in Transformer not only in NLP but also in computer vision. We wonder if transformer can be used in face recognition and whether it is better than CNNs. Therefore, we investigate the performance of Transformer models in face recognition. Considering the original Transformer may neglect the inter-patch information, we modify the patch generation process and make the tokens with sliding patches which overlaps with each others. The models are trained on CASIA-WebFace and MS-Celeb-1M databases, and evaluated on several mainstream benchmarks, including LFW, SLLFW, CALFW, CPLFW, TALFW, CFP-FP, AGEDB and IJB-C databases. We demonstrate that Face Transformer models trained on a large-scale database, MS-Celeb-1M, achieve comparable performance as CNN with similar number of parameters and MACs. To facilitate further researches, Face Transformer models and codes are available at https://github.com/zhongyy/Face-Transformer.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Responsible Face Recognition Approach for Small and Mid-Scale Systems Through Personalized Neural Networks

    cs.CV 2025-05 conditional novelty 6.0 of 10

    MOTE replaces fixed face embeddings with per-identity binary classifiers trained using KDE-generated synthetic samples, improving gender fairness and privacy at the cost of storage and enrollment time.

  2. PLGSA-Transformer: Periocular Landmark-Guided Attention with Occlusion-Adaptive Cosine Thresholding for Cross-Modal Masked and Unmasked Face Recognition

    cs.CV 2026-07 conditional novelty 5.5 of 10

    PLGSA-Transformer matches masked to unmasked faces via landmark-guided periocular attention, a hybrid CNN-Transformer, and occlusion-scaled cosine thresholds, reporting 97.2% verification accuracy on 858 images.

  3. A Flexible Approach to Augmenting a Bayesian VAR with Nonlinear Factors

    econ.EM 2025-08 unverdicted novelty 5.0 of 10

    A Bayesian VAR augmented with regression-tree nonlinear factors is proposed for parsimonious, scalable nonlinear macro forecasting and structural analysis; only the abstract could be reviewed because the full text sup...

Pith tools